/Learning Visual Representations for Perception-Action Systems

Learning Visual Representations for Perception-Action Systems

Justus Piater, Sebastien Jodogne, Renaud Detry, Dirk Kraft, Norbert Kruger, Oliver Kroemer and Jan Peters
Journal Article, International Journal of Robotics Research (IJRR), January, 2010

Download Publication (PDF)

Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author’s copyright. These works may not be reposted without the explicit permission of the copyright holder.


We discuss vision as a sensory modality for systems that effect actions in response to perceptions. While the internal representations informed by vision may be arbitrarily complex, we argue that in many cases it is advantageous to link them rather directly to action via learned mappings. These arguments are illustrated by two examples of our own work. First, our RLVC algorithm performs reinforcement learning directly on the visual input space. To make this very large space manageable, RLVC interleaves the reinforcement learner with a supervised classification algorithm that seeks to split perceptual states so as to reduce perceptual aliasing. This results in an adaptive discretization of the perceptual space based on the presence or absence of visual features. Its extension RLJC also handles continuous action spaces. In contrast to the minimalistic visual representations produced by RLVC and RLJC, our second method learns structural object models for robust object detection and pose estimation by probabilistic inference. To these models, the method associates grasp experiences autonomously learned by trial and error. These experiences form a nonparametric representation of grasp success likelihoods over gripper poses, which we call a grasp density. Thus, object detection in a novel scene simultaneously produces suitable grasping options.

BibTeX Reference
author = {Justus Piater and Sebastien Jodogne and Renaud Detry and Dirk Kraft and Norbert Kruger and Oliver Kroemer and Jan Peters},
title = {Learning Visual Representations for Perception-Action Systems},
journal = {International Journal of Robotics Research (IJRR)},
year = {2010},
month = {January},